RE: [PATCH] KVM: nVMX: Fix IRQs inject to L2 which belong to L1since race

[Hu, Robert]

> -----Original Message-----
> From: Wanpeng Li [mailto:wanpeng.li@xxxxxxxxxxxxxxx]
> Sent: Wednesday, July 2, 2014 2:54 PM
> To: Paolo Bonzini; Jan Kiszka; Gleb Natapov
> Cc: Hu, Robert; kvm@xxxxxxxxxxxxxxx; linux-kernel@xxxxxxxxxxxxxxx; Wanpeng Li
> Subject: [PATCH] KVM: nVMX: Fix IRQs inject to L2 which belong to L1 since race
> 
> This patch fix bug https://bugzilla.kernel.org/show_bug.cgi?id=72381
> 
> If we didn't inject a still-pending event to L1 since nested_run_pending,
> KVM_REQ_EVENT should be requested after the vmexit in order to inject the
> event to L1. However, current log blindly request a KVM_REQ_EVENT even if
> there is no still-pending event to L1 which blocked by nested_run_pending.
> There is a race which lead to an interrupt will be injected to L2 which
> belong to L1 if L0 send an interrupt to L1 during this window.
> 
>                VCPU0                               another thread
> 
> L1 intr not blocked on L2 first entry
> vmx_vcpu_run req event
> kvm check request req event
> check_nested_events don't have any intr
> not nested exit
>                                             intr occur (8254, lapic timer
> etc)
> inject_pending_event now have intr
> inject interrupt
> 
> This patch fix this race by introduced a l1_events_blocked field in nested_vmx
> which indicates there is still-pending event which blocked by
> nested_run_pending,
> and smart request a KVM_REQ_EVENT if there is a still-pending event which
> blocked
> by nested_run_pending.
> 
> Signed-off-by: Wanpeng Li <wanpeng.li@xxxxxxxxxxxxxxx>
Tested-by: Robert Hu<robert.hu@xxxxxxxxx>
> ---
>  arch/x86/kvm/vmx.c | 20 +++++++++++++++-----
>  1 file changed, 15 insertions(+), 5 deletions(-)
> 
> diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
> index f4e5aed..fe69c49 100644
> --- a/arch/x86/kvm/vmx.c
> +++ b/arch/x86/kvm/vmx.c
> @@ -372,6 +372,7 @@ struct nested_vmx {
>  	u64 vmcs01_tsc_offset;
>  	/* L2 must run next, and mustn't decide to exit to L1. */
>  	bool nested_run_pending;
> +	bool l1_events_blocked;
>  	/*
>  	 * Guest pages referred to in vmcs02 with host-physical pointers, so
>  	 * we must keep them pinned while L2 runs.
> @@ -7380,8 +7381,10 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu
> *vcpu)
>  	 * we did not inject a still-pending event to L1 now because of
>  	 * nested_run_pending, we need to re-enable this bit.
>  	 */
> -	if (vmx->nested.nested_run_pending)
> +	if (to_vmx(vcpu)->nested.l1_events_blocked) {
> +		to_vmx(vcpu)->nested.l1_events_blocked = false;
>  		kvm_make_request(KVM_REQ_EVENT, vcpu);
> +	}
> 
>  	vmx->nested.nested_run_pending = 0;
> 
> @@ -8197,15 +8200,20 @@ static int vmx_check_nested_events(struct
> kvm_vcpu *vcpu, bool external_intr)
> 
>  	if (nested_cpu_has_preemption_timer(get_vmcs12(vcpu)) &&
>  	    vmx->nested.preemption_timer_expired) {
> -		if (vmx->nested.nested_run_pending)
> +		if (vmx->nested.nested_run_pending) {
> +			vmx->nested.l1_events_blocked = true;
>  			return -EBUSY;
> +		}
>  		nested_vmx_vmexit(vcpu, EXIT_REASON_PREEMPTION_TIMER, 0, 0);
>  		return 0;
>  	}
> 
>  	if (vcpu->arch.nmi_pending && nested_exit_on_nmi(vcpu)) {
> -		if (vmx->nested.nested_run_pending ||
> -		    vcpu->arch.interrupt.pending)
> +		if (vmx->nested.nested_run_pending) {
> +			vmx->nested.l1_events_blocked = true;
> +			return -EBUSY;
> +		}
> +		if (vcpu->arch.interrupt.pending)
>  			return -EBUSY;
>  		nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI,
>  				  NMI_VECTOR | INTR_TYPE_NMI_INTR |
> @@ -8221,8 +8229,10 @@ static int vmx_check_nested_events(struct kvm_vcpu
> *vcpu, bool external_intr)
> 
>  	if ((kvm_cpu_has_interrupt(vcpu) || external_intr) &&
>  	    nested_exit_on_intr(vcpu)) {
> -		if (vmx->nested.nested_run_pending)
> +		if (vmx->nested.nested_run_pending) {
> +			vmx->nested.l1_events_blocked = true;
>  			return -EBUSY;
> +		}
>  		nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT, 0,
> 0);
>  	}
> 
> --
> 1.9.1

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/